Solution Architect, AWS Generative AI

Solvd Inc. is a rapidly growing AI-native consulting and technology services firm delivering enterprise transformation across cloud, data, software engineering, and artificial intelligence. Following the acquisition of Tooploox, Solvd offers end-to-end delivery, from strategic advisory and solution design to custom AI development and enterprise-scale implementation. The Solution Architect will own the technical design and outcome of an AWS-native retrieval platform engagement, including architecture, security design, API contract, cost model, and technical risk. This is a principal-level role. Solvd is an equal opportunity employer.

Responsibilities

Produce the target architecture for Amazon Bedrock Knowledge Bases with OpenSearch Serverless as the vector store, S3 as the landing zone, and the retrieval API on API Gateway and Lambda, and get it approved by client IT and Security by end of week 2; Define the security design (IAM roles and least privilege, encryption at rest and in transit, VPC and endpoint posture, secrets handling, entitlement-aware permission model for retrieval); Own the retrieval API contract and Integration Blueprint the Agent Assist provider builds against (request and response schema, versioning policy, authentication, rate limits, error semantics, citation payload); Decide and document chunking, embedding model, hybrid search, and metadata filtering strategy, including the cost model for OpenSearch Serverless minimum capacity, embedding on ingest, and re-embedding on model change; Run the end-of-Phase-1 re-baselining checkpoint from the technical side and flag any change control triggers; Cross-review the Knowledge Management Lead's taxonomy and metadata model; Author the operations design (CloudWatch metrics and alarms) and review every runbook before handover; Lead the transition readiness review in weeks 9–10 and sign the readiness checklist jointly with the client; Serve as the escalation point for engineers through hypercare

Requirements

10+ years in software or cloud engineering; 5+ years designing production systems on AWS; at least two complete generative AI or search retrieval deliveries on Amazon Bedrock or Amazon OpenSearch; Hands-on with Bedrock Knowledge Bases data sources and sync, OpenSearch Serverless vector collections, API Gateway, Lambda, IAM policy authoring, KMS, and CloudWatch; Experience designing permission-aware retrieval over Microsoft 365 content (SharePoint and Teams via Microsoft Graph with Entra app registration) or an equivalent enterprise content platform; A track record of writing architecture and API documents that a client's security team approved on first or second review; Experience as the named technical lead on a fixed-fee or fixed-scope engagement of 8–16 weeks; Able to present to CIO or VP-level audiences and to interview with the client before kickoff

Nice to have

AWS Certified Solutions Architect Professional; AWS Certified Generative AI Developer Professional; Prior work with Oracle B2C Service (RightNow) knowledge APIs or Sitecore content APIs; Experience with contact center Agent Assist integrations from any major provider; Familiarity with SOC 2 or ISO 27001 control language

Benefits

Shape real-world AI-driven projects across key industries, working with clients from startup innovation to enterprise transformation; Be part of a global team with equal opportunities for collaboration across continents and cultures; Thrive in an inclusive environment that prioritizes continuous learning, innovation, and ethical AI standards